Improved Lung Cancer Monitoring with Kalman Filter Algorithm for Tumor Growth Prediction

Aim: The aim of this research is to use the Kalman Filter algorithm for enhancing the precision of lung cancer monitoring by predicting tumour growth more accurately. Materials and Methods: Group 1 uses the Machine Learning (Linear Regression) model for predicting tumour growth, whereas Group 2 uses the Kalman Filter algorithm as an intervention. Each group has a size of 20, and two or more time periods are taken to collect the data. The accuracy, precision, recall, and F1-score of both models are compared to assess their performance. Results: The results were that the Kalman Filter algorithm performed better than the Linear Regression model with 4.6% increased accuracy, 4.4% increased precision, 4.2% increased recall, and 16.2% increased F1-score, resulting in better tumour growth prediction. Conclusion: The experimental results show that the Kalman Filter algorithm increases the accuracy of lung cancer monitoring, and it is a more reliable method to predict tumour growth than traditional machine learning models.